© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3761
    Prev
    Next
    INDEX
    Explanations

    initialisms and acronyms, especially those related to medicine, government, or police

    oai_token-act-pair · gemini-2.0-flash

    words indicating alternatives or choices

    np_token-act-pair-logits · gpt-4o-mini

    "or" in other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mxArray
    -0.81
    CodedInputStream
    -0.70
     poffible
    -0.62
    SequentialGroup
    -0.61
     raiſ
    -0.60
    новништво
    -0.60
     uſ
    -0.59
     ſeveral
    -0.57
    ghijklmnop
    -0.57
     faſt
    -0.57
    POSITIVE LOGITS
     or
    3.50
     или
    2.61
    或
    2.39
     atau
    2.31
     eller
    2.30
     oder
    2.20
    或者
    2.16
     nebo
    2.09
     یا
    2.09
     hoặc
    2.08
    Activations Density 3.227%

    No Known Activations